Unsupervised Clustering of Intradialytic Blood Pressure Patterns and Their Associations With Body Composition in Patients Undergoing Chronic Hemodialysis
Hongtae Kim, Soie Kwon, Jin Ho Hwang, Jungho Shin · 2026
Read Unsupervised Clustering of Intradialytic Blood Pressure Patterns and Their Associations With Body Composition in Patients Undergoing Chronic Hemodialysis by Hongtae Kim, Soie Kwon, Jin Ho Hwang, Jungho Shin (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13620190.txt.
Description
Kim and colleagues used machine learning in 2026 to sort blood pressure patterns during dialysis sessions and link them to body makeup in long-term dialysis patients. Pressure often swings during treatment. The team recorded pressure every thirty minutes across 928 sessions from 179 patients and let a clustering algorithm find natural groups, alongside body composition scans.
Three patterns emerged: a steep fall, a mild fall, and a rise during treatment, covering roughly a sixth, just under half, and a bit over a third of sessions. Body weight index did not differ between groups, but muscle measures rose steadily from the falling groups to the rising group, while body fat fell. The rising group carried the most extra water between cells. The links held after adjustment, suggesting pressure patterns could guide fluid targets.
Catalog record
| CREATOR | Hongtae Kim, Soie Kwon, Jin Ho Hwang, Jungho Shin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |